{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"![\"Open](\"https://colab.research.google.com/assets/colab-badge.svg\")
","metadata":{"id":"view-in-github"}},{"cell_type":"markdown","source":"This notebook based on the great work YoloX inference on Kaggle for COTS [LB 0.507] !!!please upvote\nhttps://www.kaggle.com/remekkinas/yolox-training-pipeline-cots-dataset-lb-0-507\n\nThis notebook just shows how to use colab to run the pipeline. it cannot be executed by kaggle but it successfully run on my colab pro.\n\nHere is the github link which included the execution results for your ref:\nhttps://github.com/lzziuhh/machine_learning/blob/master/YOLOX_kaggle_cots_demo.ipynb","metadata":{"id":"q4YkZCHxwTCO"}},{"cell_type":"markdown","source":"# Installing the [Kaggle API](https://github.com/Kaggle/kaggle-api) in Colab","metadata":{"id":"DIf2PtekjPtY"}},{"cell_type":"code","source":"!pip install kaggle","metadata":{"id":"OppyMnCuWjzJ","outputId":"c475412c-0403-4c56-9ae6-b138cdd6934a"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Authenticating with Kaggle using kaggle.json\n\nNavigate to https://www.kaggle.com. Then go to the [Account tab of your user profile](https://www.kaggle.com/me/account) and select Create API Token. This will trigger the download of kaggle.json, a file containing your API credentials.\n\nThen run the cell below to upload kaggle.json to your Colab runtime.","metadata":{"id":"hMY4CFezjcG-"}},{"cell_type":"code","source":"from google.colab import files\n\nuploaded = files.upload()\n\nfor fn in uploaded.keys():\n print('User uploaded file \"{name}\" with length {length} bytes'.format(\n name=fn, length=len(uploaded[fn])))\n \n# Then move kaggle.json into the folder where the API expects to find it.\n!mkdir -p ~/.kaggle/ && mv kaggle.json ~/.kaggle/ && chmod 600 ~/.kaggle/kaggle.json","metadata":{"id":"0HtGf0HEXEa5","outputId":"1c174e16-4763-468d-dfef-5e27c35d95e8"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Using the Kaggle API\n\nFor a more complete list of what you can do with the API, visit https://github.com/Kaggle/kaggle-api.","metadata":{"id":"HMk7Zz4ZkpCe"}},{"cell_type":"markdown","source":"## Listing competitions","metadata":{"id":"SHVqmMXfilWG"}},{"cell_type":"code","source":"!kaggle competitions list","metadata":{"id":"Oqt7Yfi5aQuM","outputId":"421bf12b-caac-4c34-8948-ca04f744f1ab"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Downloading a dataset","metadata":{"id":"dNke00r6ig3h"}},{"cell_type":"code","source":"# !kaggle competitions download -c tensorflow-great-barrier-reef\n#↑not works, only download about 40 pictures. \n# found dataset can be downloaded(thanks the help)\n!kaggle datasets download -d yondraco/tensorflowgreatbarrierreef","metadata":{"id":"Aojvqv8Gaf8I","outputId":"76d4276a-c7b3-43b9-c6c3-251e002cb004"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# unzip the download dataset\n!mkdir /kaggle\n!mkdir /kaggle/input\n!mkdir /kaggle/input/tensorflow-great-barrier-reef\n!unzip -q ./tensorflowgreatbarrierreef.zip -d /kaggle/input/tensorflow-great-barrier-reef","metadata":{"id":"Zruh6G1_T8z1","outputId":"983e2b6f-5a70-4766-df5b-0403a90f65f4"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Check GPU Type","metadata":{"id":"JKXGKwBrGco9"}},{"cell_type":"code","source":"gpu_info = !nvidia-smi\ngpu_info = '\\n'.join(gpu_info)\nif gpu_info.find('failed') >= 0:\n print('Not connected to a GPU')\nelse:\n print(gpu_info)","metadata":{"id":"tTf7CZejGIvF","outputId":"61d10ee9-18c3-4351-c71c-2ad8e0e2f14a"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Google drive connection","metadata":{"id":"wYGAK_lnl-EK"}},{"cell_type":"code","source":"import glob\nfrom google.colab import drive\ndrive.mount('/content/gdrive')\n\n!ln -s /content/gdrive/My\\ Drive/ /mydrive\n\n!ls /mydrive","metadata":{"id":"_BBM6Hswo868","outputId":"e84d4791-5779-4cc6-906a-ba7f87e986d2"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Train YOLOX on COTS dataset (PART 1 - TRAINING)\n\nThis notebook shows how to train custom object detection model (COTS dataset) on Kaggle. It could be good starting point for build own custom model based on YOLOX detector. Full github repository you can find here - [YOLOX](https://github.com/Megvii-BaseDetection/YOLOX)\n\n\n\n**Steps covered in this notebook:**\n* Install YOLOX \n* Prepare COTS dataset for YOLOX object detection training\n* Download Pre-Trained Weights for YOLOX\n* Prepare configuration files\n* YOLOX training\n* Run YOLOX inference on test images\n* Export YOLOX weights for Tensorflow inference (soon)\n\nNow I created notebook for learning and prototyping in YOLOX. Next step is too create better model (play with YOLOX experimentation parameters).","metadata":{"execution":{"iopub.execute_input":"2021-11-29T13:34:31.033449Z","iopub.status.busy":"2021-11-29T13:34:31.033138Z","iopub.status.idle":"2021-11-29T13:34:33.455468Z","shell.execute_reply":"2021-11-29T13:34:33.454141Z","shell.execute_reply.started":"2021-11-29T13:34:31.033368Z"},"papermill":{"duration":0.032599,"end_time":"2021-12-02T11:42:48.314913","exception":false,"start_time":"2021-12-02T11:42:48.282314","status":"completed"},"tags":[],"id":"f272af15"}},{"cell_type":"markdown","source":"\nI found that there is no reference custom model training YOLOX notebook on Kaggle (or I am bad in searching ... ). Since we have such an opportunity this is my contribution to this competition. Feel free to use it and enjoy!\n I really appreciate if you upvote this notebook. Thank you! \n
\n\n\n\nThis work consists of two parts: \n
\n \n
\n For YOLOX_s I use input size 960x960 but you can change it for your experiments. \n
","metadata":{"papermill":{"duration":0.068893,"end_time":"2021-12-02T11:45:26.585284","exception":false,"start_time":"2021-12-02T11:45:26.516391","status":"completed"},"tags":[],"id":"19227ce7"}},{"cell_type":"code","source":"config_file_template = '''\n\n#!/usr/bin/env python3\n# -*- coding:utf-8 -*-\n# Copyright (c) Megvii, Inc. and its affiliates.\n\nimport os\n\nfrom yolox.exp import Exp as MyExp\n\n\nclass Exp(MyExp):\n def __init__(self):\n super(Exp, self).__init__()\n self.depth = 0.33\n self.width = 0.50\n self.exp_name = os.path.split(os.path.realpath(__file__))[1].split(\".\")[0]\n \n # Define yourself dataset path\n self.data_dir = \"/kaggle/working/dataset/images\"\n self.train_ann = \"train.json\"\n self.val_ann = \"valid.json\"\n\n self.num_classes = 1\n\n self.max_epoch = $max_epoch\n self.data_num_workers = 2\n self.eval_interval = 1\n \n self.mosaic_prob = 1.0\n self.mixup_prob = 1.0\n self.hsv_prob = 1.0\n self.flip_prob = 0.5\n self.no_aug_epochs = 2\n \n self.input_size = (960, 960)\n self.mosaic_scale = (0.5, 1.5)\n self.random_size = (10, 20)\n self.test_size = (960, 960)\n'''","metadata":{"execution":{"iopub.execute_input":"2021-12-02T11:45:26.730435Z","iopub.status.busy":"2021-12-02T11:45:26.728686Z","iopub.status.idle":"2021-12-02T11:45:26.731104Z","shell.execute_reply":"2021-12-02T11:45:26.73154Z","shell.execute_reply.started":"2021-11-30T16:58:48.094747Z"},"papermill":{"duration":0.077486,"end_time":"2021-12-02T11:45:26.731674","exception":false,"start_time":"2021-12-02T11:45:26.654188","status":"completed"},"tags":[],"id":"623df872"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"\n I trained model for 20 EPOCHS only .... This is for DEMO purposes only. \n
","metadata":{"papermill":{"duration":0.069635,"end_time":"2021-12-02T11:45:27.160037","exception":false,"start_time":"2021-12-02T11:45:27.090402","status":"completed"},"tags":[],"id":"67e2a582"}},{"cell_type":"code","source":"PIPELINE_CONFIG_PATH='cots_config.py'\n\npipeline = Template(config_file_template).substitute(max_epoch = 20)\n\nwith open(PIPELINE_CONFIG_PATH, 'w') as f:\n f.write(pipeline)","metadata":{"execution":{"iopub.execute_input":"2021-12-02T11:45:27.303649Z","iopub.status.busy":"2021-12-02T11:45:27.302834Z","iopub.status.idle":"2021-12-02T11:45:27.304805Z","shell.execute_reply":"2021-12-02T11:45:27.305197Z","shell.execute_reply.started":"2021-11-30T16:58:53.180488Z"},"papermill":{"duration":0.076537,"end_time":"2021-12-02T11:45:27.305328","exception":false,"start_time":"2021-12-02T11:45:27.228791","status":"completed"},"tags":[],"id":"9775b2d8"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# ./yolox/data/datasets/voc_classes.py\n\nvoc_cls = '''\nVOC_CLASSES = (\n \"starfish\",\n)\n'''\nwith open('./yolox/data/datasets/voc_classes.py', 'w') as f:\n f.write(voc_cls)\n\n# ./yolox/data/datasets/coco_classes.py\n\ncoco_cls = '''\nCOCO_CLASSES = (\n \"starfish\",\n)\n'''\nwith open('./yolox/data/datasets/coco_classes.py', 'w') as f:\n f.write(coco_cls)\n\n# check if everything is ok \n!more ./yolox/data/datasets/coco_classes.py","metadata":{"execution":{"iopub.execute_input":"2021-12-02T11:45:27.45012Z","iopub.status.busy":"2021-12-02T11:45:27.449531Z","iopub.status.idle":"2021-12-02T11:45:28.121547Z","shell.execute_reply":"2021-12-02T11:45:28.121083Z","shell.execute_reply.started":"2021-11-30T16:35:30.284543Z"},"papermill":{"duration":0.747771,"end_time":"2021-12-02T11:45:28.121683","exception":false,"start_time":"2021-12-02T11:45:27.373912","status":"completed"},"tags":[],"id":"b6e1bb76","outputId":"257275c0-db22-43fd-bb7b-20ee12050b12"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 4. DOWNLOAD PRETRAINED WEIGHTS","metadata":{"papermill":{"duration":0.07208,"end_time":"2021-12-02T11:45:28.271235","exception":false,"start_time":"2021-12-02T11:45:28.199155","status":"completed"},"tags":[],"id":"0a7e64e5"}},{"cell_type":"markdown","source":"List of pretrained models:\n* YOLOX-s\n* YOLOX-m\n* YOLOX-nano for inference speed (!)\n* etc.","metadata":{"papermill":{"duration":0.069745,"end_time":"2021-12-02T11:45:28.410162","exception":false,"start_time":"2021-12-02T11:45:28.340417","status":"completed"},"tags":[],"id":"d9518b54"}},{"cell_type":"code","source":"sh = 'wget https://github.com/Megvii-BaseDetection/storage/releases/download/0.0.1/yolox_s.pth'\nMODEL_FILE = 'yolox_s.pth'\n\nif NANO:\n sh = '''\n wget https://github.com/Megvii-BaseDetection/storage/releases/download/0.0.1/yolox_nano.pth\n '''\n MODEL_FILE = 'yolox_nano.pth'\n\nwith open('script.sh', 'w') as file:\n file.write(sh)\n\n!bash script.sh","metadata":{"execution":{"iopub.execute_input":"2021-12-02T11:45:28.558065Z","iopub.status.busy":"2021-12-02T11:45:28.557244Z","iopub.status.idle":"2021-12-02T11:45:34.123496Z","shell.execute_reply":"2021-12-02T11:45:34.123042Z","shell.execute_reply.started":"2021-11-30T16:24:16.591028Z"},"papermill":{"duration":5.643821,"end_time":"2021-12-02T11:45:34.123622","exception":false,"start_time":"2021-12-02T11:45:28.479801","status":"completed"},"tags":[],"id":"50068915","outputId":"99647519-56da-4d6c-df95-9736a0fe0af4"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 5. TRAIN MODEL","metadata":{"papermill":{"duration":0.07624,"end_time":"2021-12-02T11:45:34.27709","exception":false,"start_time":"2021-12-02T11:45:34.20085","status":"completed"},"tags":[],"id":"d89ed6e1"}},{"cell_type":"code","source":"!cp ./tools/train.py ./","metadata":{"execution":{"iopub.execute_input":"2021-12-02T11:45:34.442822Z","iopub.status.busy":"2021-12-02T11:45:34.43783Z","iopub.status.idle":"2021-12-02T11:45:35.102825Z","shell.execute_reply":"2021-12-02T11:45:35.101896Z","shell.execute_reply.started":"2021-11-30T16:35:38.863551Z"},"papermill":{"duration":0.750633,"end_time":"2021-12-02T11:45:35.102993","exception":false,"start_time":"2021-12-02T11:45:34.35236","status":"completed"},"tags":[],"id":"b6ae69ee"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!python train.py \\\n -f cots_config.py \\\n -d 1 \\\n -b 32 \\\n --fp16 \\\n -o \\\n -c {MODEL_FILE} # Remember to chenge this line if you take different model eg. yolo_nano.pth, yolox_s.pth or yolox_m.pth","metadata":{"execution":{"iopub.execute_input":"2021-12-02T11:45:35.264333Z","iopub.status.busy":"2021-12-02T11:45:35.263577Z","iopub.status.idle":"2021-12-02T14:52:03.208559Z","shell.execute_reply":"2021-12-02T14:52:03.209069Z","shell.execute_reply.started":"2021-11-30T16:58:59.338486Z"},"papermill":{"duration":11188.029825,"end_time":"2021-12-02T14:52:03.209243","exception":false,"start_time":"2021-12-02T11:45:35.179418","status":"completed"},"tags":[],"id":"4639b667","outputId":"fd188c93-6e16-4bf6-a9f9-bbd32b2a6f4b"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 6. RUN INFERENCE\n\n## 6A. INFERENCE USING YOLOX TOOL","metadata":{"papermill":{"duration":0.509103,"end_time":"2021-12-02T14:52:04.061196","exception":false,"start_time":"2021-12-02T14:52:03.552093","status":"completed"},"tags":[],"id":"f2bef509"}},{"cell_type":"code","source":"# I have to fix demo.py file because it:\n# - raises error in Kaggle (cvWaitKey does not work) \n# - saves result files in time named directory eg. /2021_11_29_22_51_08/ which is difficult then to automatically show results\n\n%cp ../../input/yolox-kaggle-fix-for-demo-inference/demo.py tools/demo.py","metadata":{"execution":{"iopub.execute_input":"2021-12-02T14:52:04.927622Z","iopub.status.busy":"2021-12-02T14:52:04.926842Z","iopub.status.idle":"2021-12-02T14:52:05.677087Z","shell.execute_reply":"2021-12-02T14:52:05.676559Z","shell.execute_reply.started":"2021-11-30T17:40:23.530309Z"},"papermill":{"duration":1.104025,"end_time":"2021-12-02T14:52:05.677218","exception":false,"start_time":"2021-12-02T14:52:04.573193","status":"completed"},"tags":[],"id":"4f492aec","outputId":"11668d34-a01c-4b42-9408-3e8b144a2349"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"TEST_IMAGE_PATH = \"/kaggle/working/dataset/images/val2017/0-4614.jpg\"\nMODEL_PATH = \"./YOLOX_outputs/cots_config/best_ckpt.pth\"\n\n!python tools/demo.py image \\\n -f cots_config.py \\\n -c {MODEL_PATH} \\\n --path {TEST_IMAGE_PATH} \\\n --conf 0.1 \\\n --nms 0.45 \\\n --tsize 960 \\\n --save_result \\\n --device gpu","metadata":{"execution":{"iopub.execute_input":"2021-12-02T14:52:06.38001Z","iopub.status.busy":"2021-12-02T14:52:06.374279Z","iopub.status.idle":"2021-12-02T14:52:13.814332Z","shell.execute_reply":"2021-12-02T14:52:13.813508Z","shell.execute_reply.started":"2021-11-30T17:40:25.955415Z"},"papermill":{"duration":7.788164,"end_time":"2021-12-02T14:52:13.814488","exception":false,"start_time":"2021-12-02T14:52:06.026324","status":"completed"},"tags":[],"id":"4e3f4d08","outputId":"f48769b4-a7ef-437d-bd22-2b18ef10a106"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"OUTPUT_IMAGE_PATH = \"./YOLOX_outputs/cots_config/vis_res/2022_01_02_02_27_40/0-4614.jpg\" \nImage.open(OUTPUT_IMAGE_PATH)","metadata":{"execution":{"iopub.execute_input":"2021-12-02T14:52:14.507984Z","iopub.status.busy":"2021-12-02T14:52:14.507434Z","iopub.status.idle":"2021-12-02T14:52:14.913779Z","shell.execute_reply":"2021-12-02T14:52:14.9161Z","shell.execute_reply.started":"2021-11-30T17:40:33.95912Z"},"papermill":{"duration":0.757835,"end_time":"2021-12-02T14:52:14.917871","exception":false,"start_time":"2021-12-02T14:52:14.160036","status":"completed"},"tags":[],"id":"556c75c1","outputId":"ba674f36-1b59-4715-e7ca-13a2beec3fa9"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## 6B. INFERENCE USING CUSTOM SCRIPT (IT WOULD BE USED FOR COTS INFERENCE PART)\n\n### 6B.1 SETUP MODEL","metadata":{"papermill":{"duration":0.38768,"end_time":"2021-12-02T14:52:15.903134","exception":false,"start_time":"2021-12-02T14:52:15.515454","status":"completed"},"tags":[],"id":"96276c4a"}},{"cell_type":"code","source":"from yolox.utils import postprocess\nfrom yolox.data.data_augment import ValTransform\n\nCOCO_CLASSES = (\n \"starfish\",\n)\n\n# get YOLOX experiment\ncurrent_exp = importlib.import_module('cots_config')\nexp = current_exp.Exp()\n\n# set inference parameters\ntest_size = (960, 960)\nnum_classes = 1\nconfthre = 0.1\nnmsthre = 0.45\n\n\n# get YOLOX model\nmodel = exp.get_model()\nmodel.cuda()\nmodel.eval()\n\n# get custom trained checkpoint\nckpt_file = \"./YOLOX_outputs/cots_config/best_ckpt.pth\"\nckpt = torch.load(ckpt_file, map_location=\"cpu\")\nmodel.load_state_dict(ckpt[\"model\"])","metadata":{"execution":{"iopub.execute_input":"2021-12-02T14:52:16.685684Z","iopub.status.busy":"2021-12-02T14:52:16.6851Z","iopub.status.idle":"2021-12-02T14:52:18.762554Z","shell.execute_reply":"2021-12-02T14:52:18.762107Z","shell.execute_reply.started":"2021-11-30T17:40:47.582427Z"},"papermill":{"duration":2.471735,"end_time":"2021-12-02T14:52:18.762678","exception":false,"start_time":"2021-12-02T14:52:16.290943","status":"completed"},"tags":[],"id":"0baa2a26","outputId":"4c2c4be0-5e44-4d29-e4f4-b9d2cfc5659b"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### 6B.2 INFERENCE BBOXES","metadata":{"papermill":{"duration":0.388003,"end_time":"2021-12-02T14:52:19.541364","exception":false,"start_time":"2021-12-02T14:52:19.153361","status":"completed"},"tags":[],"id":"ad0930b8"}},{"cell_type":"code","source":"def yolox_inference(img, model, test_size): \n bboxes = []\n bbclasses = []\n scores = []\n \n preproc = ValTransform(legacy = False)\n\n tensor_img, _ = preproc(img, None, test_size)\n tensor_img = torch.from_numpy(tensor_img).unsqueeze(0)\n tensor_img = tensor_img.float()\n tensor_img = tensor_img.cuda()\n\n with torch.no_grad():\n outputs = model(tensor_img)\n outputs = postprocess(\n outputs, num_classes, confthre,\n nmsthre, class_agnostic=True\n )\n\n if outputs[0] is None:\n return [], [], []\n \n outputs = outputs[0].cpu()\n bboxes = outputs[:, 0:4]\n\n bboxes /= min(test_size[0] / img.shape[0], test_size[1] / img.shape[1])\n bbclasses = outputs[:, 6]\n scores = outputs[:, 4] * outputs[:, 5]\n \n return bboxes, bbclasses, scores","metadata":{"execution":{"iopub.execute_input":"2021-12-02T14:52:20.343251Z","iopub.status.busy":"2021-12-02T14:52:20.342511Z","iopub.status.idle":"2021-12-02T14:52:20.345414Z","shell.execute_reply":"2021-12-02T14:52:20.344939Z","shell.execute_reply.started":"2021-11-30T17:44:42.017256Z"},"papermill":{"duration":0.409989,"end_time":"2021-12-02T14:52:20.345553","exception":false,"start_time":"2021-12-02T14:52:19.935564","status":"completed"},"tags":[],"id":"905f9e55"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### 6B.3 DRAW RESULT","metadata":{"papermill":{"duration":0.386904,"end_time":"2021-12-02T14:52:21.122467","exception":false,"start_time":"2021-12-02T14:52:20.735563","status":"completed"},"tags":[],"id":"b86e4265"}},{"cell_type":"code","source":"def draw_yolox_predictions(img, bboxes, scores, bbclasses, confthre, classes_dict):\n for i in range(len(bboxes)):\n box = bboxes[i]\n cls_id = int(bbclasses[i])\n score = scores[i]\n if score < confthre:\n continue\n x0 = int(box[0])\n y0 = int(box[1])\n x1 = int(box[2])\n y1 = int(box[3])\n\n cv2.rectangle(img, (x0, y0), (x1, y1), (0, 255, 0), 2)\n cv2.putText(img, '{}:{:.1f}%'.format(classes_dict[cls_id], score * 100), (x0, y0 - 3), cv2.FONT_HERSHEY_PLAIN, 0.8, (0,255,0), thickness = 1)\n return img","metadata":{"execution":{"iopub.execute_input":"2021-12-02T14:52:21.91707Z","iopub.status.busy":"2021-12-02T14:52:21.915413Z","iopub.status.idle":"2021-12-02T14:52:21.917637Z","shell.execute_reply":"2021-12-02T14:52:21.918063Z","shell.execute_reply.started":"2021-11-30T17:40:55.800179Z"},"papermill":{"duration":0.409076,"end_time":"2021-12-02T14:52:21.918211","exception":false,"start_time":"2021-12-02T14:52:21.509135","status":"completed"},"tags":[],"id":"0d9666d4"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### 6B.4 ALL PUZZLES TOGETHER","metadata":{"papermill":{"duration":0.384862,"end_time":"2021-12-02T14:52:22.69198","exception":false,"start_time":"2021-12-02T14:52:22.307118","status":"completed"},"tags":[],"id":"b0195f53"}},{"cell_type":"code","source":"TEST_IMAGE_PATH = \"/kaggle/working/dataset/images/val2017/0-4614.jpg\"\nimg = cv2.imread(TEST_IMAGE_PATH)\n\n# Get predictions\nbboxes, bbclasses, scores = yolox_inference(img, model, test_size)\n\n# Draw predictions\nout_image = draw_yolox_predictions(img, bboxes, scores, bbclasses, confthre, COCO_CLASSES)\n\n# Since we load image using OpenCV we have to convert it \nout_image = cv2.cvtColor(out_image, cv2.COLOR_BGR2RGB)\ndisplay(Image.fromarray(out_image))","metadata":{"execution":{"iopub.execute_input":"2021-12-02T14:52:23.475501Z","iopub.status.busy":"2021-12-02T14:52:23.474738Z","iopub.status.idle":"2021-12-02T14:52:24.531926Z","shell.execute_reply":"2021-12-02T14:52:24.532371Z","shell.execute_reply.started":"2021-11-30T17:44:46.826943Z"},"papermill":{"duration":1.45195,"end_time":"2021-12-02T14:52:24.53252","exception":false,"start_time":"2021-12-02T14:52:23.08057","status":"completed"},"tags":[],"id":"bc97a7a2","outputId":"914e5435-f5dc-4ccc-b83a-8f730da37cfa"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"\n Find this notebook helpful? :) Please give me a vote ;) Thank you\n
","metadata":{"papermill":{"duration":0.450911,"end_time":"2021-12-02T14:52:25.429263","exception":false,"start_time":"2021-12-02T14:52:24.978352","status":"completed"},"tags":[],"id":"04944912"}},{"cell_type":"code","source":"","metadata":{"id":"PgXMT44Oqpdv"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 7. SUBMIT TO COTS COMPETITION AND EVALUATE","metadata":{"papermill":{"duration":0.670298,"end_time":"2021-12-02T14:52:26.579061","exception":false,"start_time":"2021-12-02T14:52:25.908763","status":"completed"},"tags":[],"id":"83f2fbcc"}},{"cell_type":"code","source":"# import greatbarrierreef\n\n# env = greatbarrierreef.make_env() # initialize the environment\n# iter_test = env.iter_test() ","metadata":{"execution":{"iopub.execute_input":"2021-12-02T14:52:27.465244Z","iopub.status.busy":"2021-12-02T14:52:27.464617Z","iopub.status.idle":"2021-12-02T14:52:27.50299Z","shell.execute_reply":"2021-12-02T14:52:27.502558Z","shell.execute_reply.started":"2021-11-30T17:41:53.605068Z"},"papermill":{"duration":0.482595,"end_time":"2021-12-02T14:52:27.503127","exception":false,"start_time":"2021-12-02T14:52:27.020532","status":"completed"},"tags":[],"id":"97202523"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# submission_dict = {\n# 'id': [],\n# 'prediction_string': [],\n# }\n\n# for (image_np, sample_prediction_df) in iter_test:\n \n# bboxes, bbclasses, scores = yolox_inference(image_np, model, test_size)\n \n# predictions = []\n# for i in range(len(bboxes)):\n# box = bboxes[i]\n# cls_id = int(bbclasses[i])\n# score = scores[i]\n# if score < confthre:\n# continue\n# x_min = int(box[0])\n# y_min = int(box[1])\n# x_max = int(box[2])\n# y_max = int(box[3])\n \n# bbox_width = x_max - x_min\n# bbox_height = y_max - y_min\n \n# predictions.append('{:.2f} {} {} {} {}'.format(score, x_min, y_min, bbox_width, bbox_height))\n \n# prediction_str = ' '.join(predictions)\n# sample_prediction_df['annotations'] = prediction_str\n# env.predict(sample_prediction_df)\n\n# print('Prediction:', prediction_str)","metadata":{"execution":{"iopub.execute_input":"2021-12-02T14:52:28.3971Z","iopub.status.busy":"2021-12-02T14:52:28.396539Z","iopub.status.idle":"2021-12-02T14:52:28.847839Z","shell.execute_reply":"2021-12-02T14:52:28.847374Z","shell.execute_reply.started":"2021-11-30T17:44:53.458871Z"},"papermill":{"duration":0.903362,"end_time":"2021-12-02T14:52:28.847979","exception":false,"start_time":"2021-12-02T14:52:27.944617","status":"completed"},"tags":[],"id":"2fb163c5"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"","metadata":{"id":"NLc--1KSKSSC"}},{"cell_type":"code","source":"# sub_df = pd.read_csv('submission.csv')\n# sub_df.head()","metadata":{"execution":{"iopub.execute_input":"2021-12-02T14:52:29.73083Z","iopub.status.busy":"2021-12-02T14:52:29.72995Z","iopub.status.idle":"2021-12-02T14:52:29.740892Z","shell.execute_reply":"2021-12-02T14:52:29.740342Z","shell.execute_reply.started":"2021-11-30T17:46:07.265368Z"},"papermill":{"duration":0.454318,"end_time":"2021-12-02T14:52:29.741041","exception":false,"start_time":"2021-12-02T14:52:29.286723","status":"completed"},"tags":[],"id":"d15df70f"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!cp -r ./YOLOX_outputs /content/gdrive/MyDrive/kaggle/YoloX/","metadata":{"id":"7rYlxPdhuS3E"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"id":"R_AHrPCNuo62"},"execution_count":null,"outputs":[]}]} 
![](\"https://github.com/Megvii-BaseDetection/YOLOX/raw/main/assets/git_fig.png\"/)